Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 2619
    Prev
    Next
    INDEX
    Explanations

    dates and time-related phrases

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to time delays and their consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ocument
    -0.71
    Role
    -0.66
    Specific
    -0.65
    PDATE
    -0.62
    acebook
    -0.61
    vertisement
    -0.59
    èĢħ
    -0.58
    istani
    -0.57
    assadors
    -0.57
    ãĤ±
    -0.57
    POSITIVE LOGITS
     seams
    0.88
     throats
    0.77
     tumble
    0.73
     winds
    0.68
     wounds
    0.67
     cliff
    0.67
     stitches
    0.64
     cliffs
    0.63
     wreckage
    0.63
     stret
    0.63
    Activations Density 0.992%

    No Known Activations